Automatic traffic sign recognition is essential in researching and developing driver assistance systems and autonomous vehicles. This paper presents the research and development of an automated traffic sign recognition module in Vietnam. The recognition model is developed based on the deep learning model YOLOv5 and incorporates architectural modifications to reduce computational complexity, increase inference speed, and meet real-time requirements for embedded system applications. The model is trained using a custom dataset collected by the research team from real-world street environments in Vietnam, encompassing diverse locations, times, and weather conditions. The trained recognition model is deployed on the Jetson embedded system, yielding high-quality recognition results and meeting real-time recognition needs.

Autonomous vehicles represent a transformative technology in modern transportation, promising enhanced safety, efficiency, and accessibility in mobility systems. This paper presents a comprehensive autonomous vehicle system designed specifically for Vietnam’s traffic conditions, featuring a multi-layered approach to perception, decision-making, and control. The system utilizes dual 2D LiDARs, camera vision, and GPS sensing to navigate complex urban environments. A key contribution is the development of a specialized segmentation model that accurately identifies Vietnam-specific traffic signs, lane markings, road features, and pedestrians. The system implements a hierarchical decision-making architecture, combining long-term planning based on GPS and map data with short-term reactive planning derived from a bird’s-eye view transformation of segmentation and LiDAR data. The control system modulates the speed and steering angle through a validated model that ensures stable vehicle operation across various traffic scenarios. Experimental results demonstrate the system’s effectiveness in real-world conditions, achieving a high accuracy rate in terms of segmentation and detection and an exact response in navigation tasks. The proposed system shows robust performance in Vietnam’s unique traffic environment, addressing challenges such as mixed traffic flow and country-specific road infrastructure.

The design and control of lower-limb rehabilitation robots for patients after a stroke has gained significant attention. This paper presents the dynamic analysis and control of a 3-degrees-of-freedom lower-limb rehabilitation robot using combined position–force control based on the force feed-forward and compensative gravity proportional derivative methods. In the lower-limb rehabilitation robot, the interaction force between the patient with the joints and links of the robot is uncertain and nonlinear due to the disturbance effect of Coriolis force, centrifugal force, gravitational force, and friction force. During recovery stages, the forces exerted by the patient’s lower limbs are also considered disturbances. Therefore, to meet the quality requirements in using the rehabilitation robot with different recovery stages of patient training, combining position control and force control is essential. In this paper, we proposed a combination of proportional–derivative gravity compensation motion control and force feed-forward control to form an advanced combined controller (position–force feed-forward control—PFFC) for a 3 DOF lower-limb functional rehabilitation robot. The forces can be sensed using a 3-axis force sensor. In addition, the robot’s position parameters are also measured by encoders. The control algorithm is implemented on the STM32F4 Discovery board. A verified test of the proposed control method is shown in the experiments, showing the good performance of the system.

This paper presents the development of a new 6-DOF parallel-kinematic motion simulator. The moving platform is connected to the base by six PUS (Prismatic-Universal-Spherical) serial chains. Comparing with the well-known Stewart-Gough platform-type motion simulator, it uses commercialized linear actuators mounted on the fixed base whereas a 6-UPS manipulator uses telescopic linear ones. Therefore, the proposed motion simulator has the advantages of lower inertia and easier fabrication over a 6-UPS counterpart. The inverse position, Jacobian and workspace analyses are performed. Using inclined arrangement of universal joints, the workspace is greatly increased. The prototype motion simulator and real-time controller using xPC have been developed. Basic six-axis motion test with the ride of single operator has been successfully performed.

Mobile robots have many industrial applications, including security, food service, and fire safety. Detecting smoke and fire quickly for early warning and monitoring is crucial in every industrial safety system. In this paper, a method for early smoke and fire detection using mobile robots equipped with cameras is presented. The method employs artificial intelligence for trajectory planning and navigation, and focus is given to detection and localization techniques for mobile robot navigation. A model of a mobile robot with Omni wheels and a modified YOLOv5 algorithm for fire and smoke detection is also introduced, which is integrated into the control system. This research addresses the issue of distinct objects of the same class by assigning each object a unique identification. The implementation not only detects fire and smoke but also identifies the position of objects in three-dimensional space, allowing the robot to map its environment incrementally for mobile navigation. The experimental results demonstrate the high accuracy achieved by the proposed method in identifying smoke and fire.

We report a flexible and noninvasive method based on field‐effect transistors hybridizing semiconducting single‐walled carbon nanotubes for monitoring the effects of histamine on Ca²⁺ release from the intracellular stores of a nonexcitable cell. These nanodevices allowed us to evaluate the real‐time electrophysiological activities of HeLa cells under the stimulation of histamine via the recording of the conductance changes of the devices. These changes resulted from the binding of histamine to its receptor type 1 on the HeLa cell membrane. Moreover, the effects of chlorphenamine, an antihistamine, on the electrophysiological activities of a single HeLa cell were also evaluated, indicating that the pretreatment of the cell with chlorpheniramine decreased intracellular Ca²⁺ release. Significantly, we only utilized a single nanodevice to perform the measurements for multiple cells pretreated with various concentrations of chlorphenamine. This enabled the statistically meaningful analysis of drug effects on cells without errors from device variations. Obtained results indicated the novel advantages of our method such as real‐time monitoring and quantitative capability. Our devices, therefore, can be efficient tools for biomedical applications such as electrophysiology research and drug screening.